Most people know about flash technology from its consumer use in iPods, smartphones, tablets and laptops. The explosion of the connected consumer is what drove the price of flash down, making it viable for enterprise deployments. What differentiates flash from disk is that it has higher performance, lower latency and lower power requirements. Layman’s terms: better experience, less waiting, lower cost. Different applications have different needs for these three characteristics. Therefore, with different required criteria there is an endless array of design architectures that can be optimized. The writing is on the wall, in perfect bold penmanship: Flash is going to play a pivotal role in software-led storage.

Flash is disruptive to disk and tape. The advantages of flash technology permeate through flash’s ability to outperform and at a lower cost. It has been five years since flash storage was introduced (Fusion-io in 2007 and EMC added enterprise-class flash to storage arrays in 2008) and flash distribution is being accelerated by software-led hybrid and server solutions. Wikibon’s research has shown that the hybrid approach of flash as a front-end (flash-first) storage solution in virtualized environments performs extremely well. In fact, in high performance environments the hybrid approach is clearly superior, both in cost and performance. These hybrid solutions use a higher percentage of flash (typically 20 percent-40 percent) and dense SATA (no SAS) for capacity, and are poised to shake-up the traditional disk arrays.

Big Data is positioning vendors to compete frantically in the flash storage space, as CIO’s and CTO’S alike are changing fundamental things about their IT departments. Flash storage is radically changing systems and more importantly application design. As it were, flash’s role in storage is half jester, half future-king. Today’s enterprise infrastructure limits application value. In an excerpt from a recent Wikibon blog post about flash Dave Vellante explained exactly what that value is:

The value IT brings to an organization flows directly from the application to the business and is measured in terms of the productivity of the organization. Infrastructure in-and-of itself delivers no direct value; however the applications, which run on infrastructure directly affect business value. Value comes in many forms but at the highest level it’s about increasing revenue and/or cutting costs; and ultimately delivering bottom line profits.

That flow from the application to the business is something that flash fixes for IT. For over 15 years functions have been moved out of the processor into the array, to share data, protect information and offload servers. However with flash, those functions are moving back, closer to the server – promising new levels of application performance and flexibility for IT. Application value and performance are increasing. Flash will reside at the server level, in all-flash and/or hybrid arrays – virtually throughout the entire stack. Here is the key: the control point changes, switching from the slow storage array to the fast server.

As a result (drum roll please) … application design will change.

Database structure will be flatter, allowing secure, multi-tenant access to the single database of record. These improved data architectures will accommodate transactional and analytic data that will allow machines to make decisions. Flash storage will in essence allow machines to change prices in near real time based on market conditions. Can you imagine the amount of physical costs that are saved in a scenario where organizational workflow can be flexibly changed in a few days or less, opposed to a few months? Companies will be able to respond much quicker to market opportunities, competitive threats, disasters, etc. The possibilites are legitimately endless.

Flash will allow systems and applications to analyze and act on massive streams of data in near real-time. What role does it play in storage you ask? A big one, Johnny. A big one.